CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-ai-voicelive-ts

Azure AI Voice Live SDK for JavaScript/TypeScript. Build real-time voice AI applications with bidirectional WebSocket communication.

74

2.77x
Quality

37%

Does it follow best practices?

Impact

100%

2.77x

Average score across 6 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/azure-ai-voicelive-ts/SKILL.md

The canonical home for this skill is azure-ai-voicelive-ts in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

42%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill excels at actionability with concrete, executable TypeScript examples covering all major use cases. However, it suffers significantly from verbosity and poor progressive disclosure — the content is a monolithic document with duplicated sections (function calling appears twice, session config shown twice) and extensive reference tables that should be in separate files. The workflow lacks explicit validation checkpoints for a real-time WebSocket system where connection reliability matters.

Suggestions

Extract reference tables (voice options, audio formats, models, key types) and the full event handler catalog into separate reference files, keeping only the Quick Start and essential patterns in SKILL.md

Remove the duplicate function calling section — it's fully covered in the Event Handling section already

Add explicit validation checkpoints to the workflow: verify session connection before configuring, confirm session update before sending audio, and include a reconnection pattern for dropped WebSocket connections

Consolidate the two session configuration examples into one, removing the redundant repetition of tools/modalities/voice settings

DimensionReasoningScore

Conciseness

The content is extremely verbose at ~400+ lines, with significant redundancy. The function calling example appears twice (once in Event Handling and again in its own section). Voice options, audio formats, models, and types reference tables add bulk that could be in separate reference files. Session configuration is shown twice with overlapping content.

1 / 3

Actionability

The skill provides fully executable TypeScript code examples throughout — authentication, session creation, event handling, function calling, and error handling are all copy-paste ready with concrete imports, method calls, and realistic parameters.

3 / 3

Workflow Clarity

The Quick Start shows a reasonable sequence (create client → start session → configure → subscribe → send audio), but there are no explicit validation checkpoints. For a WebSocket-based real-time system, there's no guidance on verifying connection success before sending audio, no reconnection strategy, and no feedback loop for handling failures during streaming.

2 / 3

Progressive Disclosure

This is a monolithic wall of content with everything inlined — reference tables, full event handler listings, duplicate function calling examples, browser usage, logging, etc. Despite having a Reference Links section at the bottom, the SKILL.md itself should be a concise overview pointing to separate files for the detailed API reference, event catalog, and examples.

1 / 3

Total

7

/

12

Passed

Description

32%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies a specific SDK and technology stack but reads more like a tagline than a functional skill description. It lacks concrete actions the skill enables, misses common user trigger terms related to voice/audio processing, and critically omits any 'Use when...' guidance for skill selection.

Suggestions

Add a 'Use when...' clause specifying triggers like 'Use when the user needs to build voice applications with Azure, implement real-time audio streaming, or work with the Azure AI Voice Live SDK in JavaScript/TypeScript projects'.

List specific concrete actions such as 'Set up WebSocket connections for audio streaming, configure voice input/output pipelines, handle real-time transcription and synthesis, manage session lifecycle'.

Include natural user keywords like 'speech-to-text', 'text-to-speech', 'audio streaming', 'voice chat', 'conversational AI', 'Azure Cognitive Services' to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain (Azure AI Voice Live SDK) and mentions a key action ('Build real-time voice AI applications with bidirectional WebSocket communication'), but doesn't list multiple concrete actions like 'stream audio', 'transcribe speech', 'synthesize voice responses', etc.

2 / 3

Completeness

Describes what the skill is about (Azure AI Voice Live SDK for building voice AI apps) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also only partially described, warranting a 1.

1 / 3

Trigger Term Quality

Includes some relevant keywords like 'Azure', 'voice', 'real-time', 'WebSocket', 'JavaScript', 'TypeScript', but misses common user variations like 'speech-to-text', 'text-to-speech', 'audio streaming', 'voice chat', 'conversational AI', or 'Azure Cognitive Services'.

2 / 3

Distinctiveness Conflict Risk

The mention of 'Azure AI Voice Live SDK' is fairly specific and distinguishes it from generic voice or audio skills, but 'real-time voice AI applications' could overlap with other voice/audio SDK skills or WebSocket communication skills.

2 / 3

Total

7

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.